domains / families / research / torchforge

torchforge

separate

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

When to use

• Clean separation between RL algorithms and infrastructure
• PyTorch-native abstractions (no Ray dependency)
• Easy algorithm experimentation (GRPO, DAPO, SAPO in ~100 lines)
• Scalable training with Monarch actor system
• Integration with TorchTitan for model parallelism
• You need production-ready stability → use **miles** or **verl**
• You want Megatron-native training → use **slime**
• torchforge is experimental and APIs may change

When not to use

• Production-ready stability
• Megatron-native training

Skill page

Source